Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1341768 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0675. Min Act: -0.0000

Data Index: 168507 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9990. Min Act: -0.0000

Data Index: 129870 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1020288 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0191. Min Act: -0.0000

Data Index: 160598 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1015452 (The Pile)

Max Activating Token Index: 724

Text #6

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1830787 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9055. Min Act: -0.0000

Data Index: 500404 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9443. Min Act: -0.0000

Data Index: 481349 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8763. Min Act: -0.0000

Data Index: 515711 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8550. Min Act: -0.0000

Data Index: 83987 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1965180 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 1.0675. Min Range: -1.0675

Max Act: 1.0274. Min Act: -0.0000

Data Index: 106305 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8355. Min Act: -0.0000

Data Index: 212211 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8784. Min Act: -0.0000

Data Index: 84003 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8424. Min Act: -0.0000

Data Index: 683370 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1618519 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1921661 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8332. Min Act: -0.0000

Data Index: 888320 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.0675. Min Range: -1.0675

Max Act: 0.8343. Min Act: -0.0000

Data Index: 665857 (The Pile)

Max Activating Token Index: 195